Intelligent monitoring method and system for the whole process of luggage accessories production

By analyzing pressure data and flow data, combining different scales and flow data, the accuracy of the monitoring results of die-casting machine operation data is solved, and the quality of luggage and accessories production is guaranteed.

CN118551939BActive Publication Date: 2024-11-05GUANGDONG XIANGSHENG BOX TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410985197.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-05
Estimated Expiration
2044-07-23

AI Technical Summary

Technical Problem

The existing technology has failed to effectively monitor the results of die-casting machine operation data, which makes it difficult to ensure the production quality of luggage and accessories.

Method used

Using intelligent monitoring method for the whole process of production of bag accessories, the stability, reliability and significance of pressure data points are analyzed by obtaining pressure data and metal liquid flow data, combining different scales and flow data to reduce the impact of noise and determine the monitoring results. and issue an alarm.

Benefits of technology

Improve the accuracy and accuracy of monitoring results, promptly detect abnormal data points, and ensure the production quality of luggage accessories.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118551939B_ABST
    Figure CN118551939B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of data processing technology, and in particular to a method and system for intelligently monitoring the progress of the entire production process of luggage accessories. The method includes: obtaining pressure data of a luggage accessories die-casting machine and flow data of a metal liquid, presetting a characteristic data segment of a pressure data point at an initial scale, determining the stability of the pressure data point in the characteristic data segment, determining the Pearson correlation coefficient between the pressure data and the flow data in the characteristic data segment, and calculating the reliability of the pressure data point; obtaining the preset number of scales of the pressure data, determining the number of inter-scale expansions of the characteristic data segment of each pressure data point; sequentially expanding the two sides of the characteristic data segment outward by the number of inter-scale expansions, obtaining the length of the characteristic data segment of the pressure data point at each scale, and determining the significance value of the pressure data point; and determining the monitoring result based on the comparison result of the significance value of the pressure data point with the preset threshold, which can effectively improve the accuracy of the monitoring result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for intelligently monitoring the progress of the entire production process of luggage accessories. Background Art

[0002] Luggage accessories are an important part of luggage, and their demand increases with the growth of the luggage industry. The quality of luggage accessories produced by die-casting machines is directly related to the service life and user experience of the entire luggage. In the process of producing luggage accessories by die-casting machines, by introducing advanced intelligent monitoring systems and real-time monitoring of production progress and production links, problems in the production process can be discovered and solved in a timely manner, thereby improving the quality of luggage accessories.

[0003] The patent application document with publication number CN116360312A discloses a monitoring system for an aluminum-magnesium alloy die-casting workshop, which includes a magnesium alloy melting gas furnace monitoring unit, a die-casting machine monitoring unit, a mold temperature controller monitoring unit, etc. Among them, the die-casting machine monitoring unit includes a die-casting machine operation display page, a die-casting machine remote control page, and a die-casting machine production die-casting prediction block, which can realize intelligent monitoring and management.

[0004] The die-casting machine will have abnormal pressure data during the production process, which directly affects the quality and internal density of luggage accessories. Therefore, close monitoring is required during the production process to ensure the quality of luggage accessories. In the above-mentioned prior art, although it is recorded that the die-casting machine operation display page and control page are realized through the die-casting machine monitoring unit during the production process of the die-casting machine, it does not solve how to obtain the operation monitoring results through the die-casting machine operation data to ensure the production quality of luggage accessories.

[0005] Based on this, how to obtain operation monitoring results through die-casting machine operation data to ensure the production quality of luggage accessories is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0006] In order to solve the technical problem of how to obtain operation monitoring results through die-casting machine operation data to ensure the production quality of luggage accessories, the present invention provides a method and system for intelligently monitoring the progress of the entire production process of luggage accessories.

[0007] In the first aspect, the present invention provides a method for intelligently monitoring the progress of the entire production process of luggage accessories, which adopts the following technical solutions:

[0008] The intelligent monitoring method for the progress of the whole process of luggage accessories production includes the following steps:

[0009] The pressure data of the die-casting machine for luggage accessories and the flow data of the metal liquid are obtained, wherein the pressure data contains a plurality of pressure data points; with each of the pressure data points as the center, a characteristic data segment of the pressure data point under the initial scale is preset, and the stability of the pressure data point in the characteristic data segment is determined, and the stability is negatively correlated with the variance of all the pressure data points in the characteristic data segment; the Pearson correlation coefficient between the pressure data and the flow data in the characteristic data segment is determined, the maximum value of the Pearson correlation coefficient is obtained, and the absolute difference between the Pearson correlation coefficient and the maximum value of the Pearson correlation coefficient is obtained, and the maximum value of the Pearson correlation coefficient is 1; and the pressure data is calculated. The reliability of the point, the reliability is positively correlated with the stability and negatively correlated with the absolute difference; the preset number of scales of the pressure data is obtained, and the number of scale expansions of the characteristic data segment of each pressure data point is determined, and the number of scale expansions is negatively correlated with the reliability of the pressure data point; the two sides of the characteristic data segment are expanded outward by the number of scale expansions in turn, and the length of the characteristic data segment of the pressure data point at each scale is obtained respectively, and the significance value of the pressure data point is determined, and the significance value is positively correlated with the stability mean of the pressure data point in the characteristic data segment at each scale; and the monitoring result is determined according to the comparison result of the significance value of the pressure data point with the preset threshold.

[0010] The present invention takes into account that the monitoring results obtained at a single scale may be accidental. Therefore, the scale values ​​of pressure data points at different scales are calculated and combined to obtain the significance values ​​of the pressure data points for monitoring, thereby effectively improving the accuracy of the obtained monitoring results. In addition, the present invention also takes into account that there may be noise data in the pressure data, which may cause misjudgment of the monitoring results. Therefore, in the process of calculating each scale value, flow data that is correlated with the pressure data is further combined to reduce the impact of noise data on the scale value, thereby effectively improving the accuracy of the obtained scale value, thereby improving the accuracy of the monitoring results.

[0011] According to the intelligent monitoring method for the progress of the entire production process of luggage accessories provided by the present invention, the step of obtaining the pressure data of the die-casting machine of luggage accessories and the flow data of the metal liquid also includes: obtaining the initial pressure data of the die-casting machine and the initial flow data of the metal liquid through a collection device, pre-processing the initial pressure data and the initial flow data to obtain the pressure data of the die-casting machine and the flow data of the metal liquid.

[0012] The present invention takes into account that the original data obtained by the acquisition device is not conducive to subsequent data processing, so by pre-processing the original data, the pressure data and flow data to be processed are obtained, thereby improving the overall quality of the data.

[0013] According to the method for intelligently monitoring the progress of the entire production process of luggage accessories provided by the present invention, the stability of the pressure data point in the characteristic data segment satisfies the relationship:

[0014] ; In the formula, Indicates The stability of each pressure data point, Indicates The variance of all pressure data points in the characteristic data segment of pressure data points, Indicates In the characteristic data segment of pressure data points, except The variance of other pressure data points besides the pressure data points, Indicates The number of all pressure data points in the characteristic data segment of pressure data points, It represents the slope of the line connecting the starting pressure data point and the ending pressure data point in the characteristic data segment. Indicates the first The pressure data point is The slope of the line connecting the pressure data points, represents the hyperparameter, represents the normalization function, Represents the absolute value symbol.

[0015] According to the method for intelligently monitoring the progress of the entire production process of luggage accessories provided by the present invention, the reliability of the pressure data point is calculated, including: obtaining a flow data point at the same sampling time as the pressure data point in the flow data;

[0016] ;

[0017] In the formula, Indicates The reliability of each pressure data point, Indicates The stability of each pressure data point, Indicates The pressure value of each pressure data point, Indicates The flow value corresponding to the pressure data point is Indicates The mean pressure of the characteristic data segment of the pressure data points, Indicates The characteristic data segment of each pressure data point corresponds to the mean flow rate of the sampling time period in the flow data. Represents the Pearson correlation coefficient of pressure data and flow data, represents the hyperparameter, and Both represent preset adjustment factors. represents the normalization function, represents the exponential function with base e, Represents the absolute value symbol.

[0018] The present invention takes into account the impact of noise data on monitoring results, and therefore introduces flow data that is correlated with pressure data to jointly determine the stability of pressure data, so as to distinguish abnormal data from noise data in the pressure data, thereby accurately obtaining true abnormal data and facilitating subsequent monitoring.

[0019] According to the intelligent monitoring method for the progress of the entire production process of luggage accessories provided by the present invention, the number of expansions between the scales satisfies the relationship:

[0020] ;

[0021] In the formula, Indicates The number of inter-scale expansions of pressure data points, Indicates The reliability of each pressure data point, Indicates the number of expansions between preset scales, Indicates the round-up symbol. Represents an exponential function with base e.

[0022] The present invention provides a precise calculation method for the number of inter-scale expansions of pressure data points, which can accurately obtain the number of inter-scale expansions of pressure data points, and is used for subsequent expansion of characteristic data segments of pressure data points to obtain characteristic data segments of pressure data points at various scales.

[0023] According to the method for intelligently monitoring the progress of the entire production process of luggage accessories provided by the present invention, the determination of the significance value of the pressure data point includes: taking the stability mean of all pressure data points in the characteristic data segment of the pressure data point at each scale as the characteristic value of the pressure data point at the corresponding scale; taking the mean of the difference between the pressure data point and the characteristic value of each pressure data point in the characteristic data segment as the scale value of the pressure data point; calculating the significance value of the pressure data point:

[0024] ;

[0025] In the formula, Indicates The significance value of each pressure data point, Indicates the number of preset scales, Indicates The pressure data point is The scale value under each scale.

[0026] According to the method for intelligently monitoring the progress of the entire production process of luggage accessories provided by the present invention, the monitoring result is determined based on the comparison result of the significance value of the pressure data point with a preset threshold, including: when the significance value of the pressure data point is greater than or equal to the preset threshold, the monitoring result of the pressure data point is an abnormal data point; when the significance value of the pressure data point is less than the preset threshold, the monitoring result of the pressure data point is a normal data point.

[0027] The present invention can accurately obtain the significance value of the pressure data point by combining the scale values ​​of the pressure data point at multiple scales, and compare it with the threshold value to obtain the final monitoring result.

[0028] According to the method for intelligently monitoring the progress of the entire production process of luggage accessories provided by the present invention, after determining the monitoring results, it also includes: obtaining the proportion of all abnormal data points in the pressure data in the pressure data, and issuing an alarm when the proportion exceeds a preset alarm threshold.

[0029] The present invention takes into account that the existence of abnormal data points may affect the production process, resulting in poor quality of luggage accessories. Therefore, when it is monitored that the proportion of abnormal data points exceeds the preset alarm threshold, an alarm is promptly issued to facilitate staff to take timely action, reduce the risk of equipment operation, and ensure the quality of luggage accessories.

[0030] In the second aspect, the present invention provides an intelligent monitoring system for the progress of the entire production process of luggage accessories, which adopts the following technical solutions:

[0031] The system for intelligently monitoring the progress of the entire production process of luggage accessories comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method for intelligently monitoring the progress of the entire production process of luggage accessories is implemented.

[0032] By adopting the above technical solution, the above-mentioned method for intelligently monitoring the progress of the entire process of luggage accessories production is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is manufactured based on the memory and the processor for easy use.

[0033] The present invention has the following technical effects:

[0034] Based on the above technical scheme, when obtaining the monitoring results of pressure data in the production process of luggage accessories, the present invention combines the scale values ​​of pressure data points at different scales to obtain the significance values ​​of pressure data points and monitors them, thereby avoiding the contingency of monitoring results obtained at a single scale and effectively improving the accuracy of the obtained monitoring results; on this basis, in the process of calculating each scale value, the present invention further combines flow data that is correlated with pressure data, reduces the influence of noise data on the scale value, effectively improves the accuracy of the obtained scale value, and thus improves the accuracy of the monitoring results. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0036] Figure 1 A schematic flow chart of a method for intelligently monitoring the progress of the entire production process of luggage accessories provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0038] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0039] It should be noted that the die-casting machine may have abnormal pressure data during the production process, and these abnormal pressure data will directly affect the quality and internal density of luggage accessories. Therefore, the pressure data needs to be closely monitored during the production process to ensure the quality of luggage accessories. The present invention takes into account that the monitoring results of the pressure data obtained under a single scale may be accidental. Based on this, the present invention obtains the monitoring results by analyzing the pressure data points under different scales. Among them, the length of the characteristic data segment under each scale is different, and the length difference of the characteristic data segment between adjacent scales is the number of expansions between scales, and the size of the number of expansions between scales affects the accuracy of the monitoring results. If the number of expansions between scales of the pressure data points with higher reliability is too large, it may be overly diluted in the process of obtaining the significance value and thus obtaining the monitoring results, reducing the influence of the pressure data points with higher reliability on the monitoring results, thereby reducing the accuracy of the monitoring results; if the number of expansions between scales of the pressure data points with lower reliability is too small, it is impossible to introduce enough pressure data from different scales for further verification, which will also reduce the accuracy of the monitoring results.

[0040] Based on this, the embodiment of the present invention discloses a method for intelligently monitoring the progress of the entire production process of luggage accessories. Figure 1 As shown, Figure 1 The flowchart of the intelligent monitoring method for the progress of the whole process of luggage accessories production provided by the embodiment of the present invention includes the following steps S1 to S5. The present invention presets the characteristic data segments of each pressure data point at the initial scale, analyzes the change and reliability of the characteristic data segments of the pressure data points at the initial scale, thereby obtaining the number of expansions between scales of the pressure data points, and obtains the scale value of the pressure data points at each scale through the expanded characteristic data segments to obtain the monitoring results.

[0041] Among them, in order to reduce the impact of noise data in pressure data on monitoring results, parameters related to pressure data can be obtained in the production of luggage accessories, and the correlation between the flow data of metal liquid and the pressure data of the die-casting machine is strong, and the two are positively correlated. If the flow rate of metal liquid is high, it means that the speed of metal liquid in the mold cavity is fast and the filling time is short. In order to ensure that the metal liquid can fully fill the entire mold cavity, the die-casting machine needs to increase the pressure to adapt to the flow change. The present invention can reduce the impact of noise data by combining the flow data of metal liquid with the pressure data of the die-casting machine, and effectively improves the accuracy of the number of scale expansions of pressure data points, so that the subsequent monitoring results can be accurately obtained.

[0042] The technical solution provided by the embodiment of the present invention is described in detail below:

[0043] S1: Obtain the pressure data and metal liquid flow data of the die-casting machine for luggage accessories.

[0044] It should be noted that in order to reduce the impact of noise data in the pressure data on the monitoring results, the abnormal data and noise data in the pressure data can be screened by introducing data that is correlated with the pressure data, so that the reliability of each pressure data point can be accurately obtained.

[0045] The pressure data includes a plurality of pressure data points, and the flow data includes a plurality of flow data points, and the pressure data points correspond to the flow data points one by one.

[0046] For example, in an embodiment of the present invention, before obtaining the pressure data of the die-casting machine for luggage accessories and the flow data of the metal liquid, the initial pressure data of the die-casting machine and the initial flow data of the metal liquid can also be obtained through an acquisition device, and the initial pressure data and the initial flow data can be preprocessed to obtain the pressure data of the die-casting machine and the flow data of the metal liquid.

[0047] For example, the data preprocessing method can be to obtain the initial pressure data of the die-casting machine and the initial flow data of the metal liquid through the acquisition equipment, and then use the analog-to-digital conversion equipment to convert the initial data into digital form to facilitate subsequent data processing. The specific settings can be made according to actual needs.

[0048] Among them, pressure sensors can be used to collect pressure data of the die-casting machine, and flow sensors can be used to collect flow data of the metal liquid; in order to facilitate subsequent data processing, the collection parameters of pressure data and flow data can be consistent, and the collection parameters can include one or more of collection duration, collection frequency, collection cycle, etc., which can be set according to actual needs.

[0049] For example, the data collection duration may be 30 minutes, and the collection frequency may be once every five seconds. The collection duration and the collection frequency may be set according to actual needs.

[0050] S2: Taking each pressure data point as the center, presetting a characteristic data segment of the pressure data point under the initial scale, and determining the stability of the pressure data point in the characteristic data segment.

[0051] It should be noted that in order to accurately obtain the reliability of each pressure data point, the local trend and pattern of the surrounding data of the pressure data point can be obtained to verify the pressure data point, thereby improving the accuracy of the reliability of the pressure data point. Based on this, the characteristic data segment of the pressure data point under the preset initial scale can be used to analyze the changes in the pressure data point and the corresponding characteristic data segment to obtain the stability of the pressure data point, and the stability can be corrected in combination with the correlation between the pressure data and the flow data, thereby accurately obtaining the reliability of the pressure data point. The smaller the change between the pressure data point and the corresponding characteristic data segment, the higher the stability of the pressure data point.

[0052] For example, when a characteristic data segment of a pressure data point at an initial scale is preset, a number of other pressure data points can be equally acquired on both sides of the pressure data point with each pressure data point as the center. The pressure data point and the other pressure data points together constitute the characteristic data segment of the pressure data point at the initial scale.

[0053] For example, when the characteristic data segment of the pressure data point is preset at the initial scale, 20 other pressure data points can be obtained on both sides of the pressure data point, and the length of the characteristic data segment of the obtained pressure data point is 41. If the number of pressure data points on one side is insufficient during the acquisition process, it is supplemented on the other side.

[0054] For example, in an embodiment of the present invention, stability is negatively correlated with the variance of all pressure data points in the characteristic data segment. To determine the stability of the pressure data point in the characteristic data segment, please refer to the following formula:

[0055] ;

[0056] In the formula, Indicates The stability of each pressure data point, Indicates The variance of all pressure data points in the characteristic data segment of pressure data points, Indicates In the characteristic data segment of pressure data points, except The variance of other pressure data points besides the pressure data points, Indicates The number of all pressure data points in the characteristic data segment of pressure data points, It represents the slope of the line connecting the starting pressure data point and the ending pressure data point in the characteristic data segment. Indicates the first The pressure data point is The slope of the line connecting the pressure data points, represents the hyperparameter, represents the normalization function, Represents the absolute value symbol.

[0057] In the above formula, Indicates removal of The difference in the variance of the characteristic data segment before and after the pressure data point. The larger the value, the The existence of pressure data points will reduce the variance in the characteristic data segment, and the data distribution and changes will be more stable. The stability of each pressure data point also increases accordingly.

[0058] Indicates the first The pressure data point is The absolute difference between the slope of the line connecting the pressure data points and the slope of the line connecting the starting pressure data point and the ending pressure data point in the characteristic data segment. The smaller the value, the smaller the gap between the change of adjacent pressure data points and the overall change of the characteristic data segment, the smoother the change between the pressure data points in the characteristic data segment, and the higher the credibility of the stability of the pressure data point.

[0059] It can be 0.001, which can be set according to actual needs. The existence of hyperparameters is to avoid the situation where the denominator in the above formula is 0.

[0060] The stability of the pressure data point obtained based on the above formula is determined based on the data changes of the pressure data point and its own characteristic data segment. It can only roughly distinguish normal data from abnormal data in the pressure data. However, the abnormal data includes abnormal data and noise data generated by the system itself that need to be judged. The stability of the pressure data point cannot distinguish abnormal data from pressure data. Therefore, it is necessary to introduce a new parameter to correct the stability, so as to distinguish abnormal data from noise data, that is, perform the following steps:

[0061] S3: Determine the Pearson correlation coefficient between the pressure data and the flow data in the characteristic data segment, and calculate the reliability of the pressure data point.

[0062] It should be noted that there is a good positive correlation between the pressure data and the flow data. If the flow rate of the metal liquid increases, the pressure of the die-casting machine will increase accordingly; conversely, if the flow rate of the metal liquid decreases, the pressure of the die-casting machine will also decrease accordingly.

[0063] Among them, the reliability and stability of the pressure data point are positively correlated, and negatively correlated with the absolute difference between the Pearson correlation coefficient and the maximum value of the Pearson correlation coefficient.

[0064] For example, in an embodiment of the present invention, when calculating the reliability of a pressure data point, a flow data point at the same sampling time as the pressure data point can be obtained in the flow data; the Pearson correlation coefficient between the pressure data and the flow data in the characteristic data segment is determined, the maximum value of the Pearson correlation coefficient is obtained, the absolute difference between the Pearson correlation coefficient and the maximum value of the Pearson correlation coefficient is obtained, and the reliability of the pressure data point is calculated.

[0065] For example, the reliability of calculating the pressure data point can be specifically referred to the following formula:

[0066] ;

[0067] In the formula, Indicates The reliability of each pressure data point, Indicates The stability of each pressure data point, Indicates The pressure value of each pressure data point, Indicates The flow value corresponding to the pressure data point is Indicates The mean pressure of the characteristic data segment of the pressure data points, Indicates The characteristic data segment of each pressure data point corresponds to the mean flow rate of the sampling time period in the flow data. Represents the Pearson correlation coefficient of pressure data and flow data, represents the hyperparameter, and Both represent preset adjustment factors. represents the normalization function, represents the exponential function with base e, Represents the absolute value symbol.

[0068] In the above formula, the maximum value of the Pearson correlation coefficient is 1; It can be 0.001. The existence of hyperparameters is to avoid the situation where the denominator of the above formula is 0, which makes the formula meaningless. The value of the hyperparameter can be set according to actual needs; preset adjustment factor Can be 1.5, preset adjustment factor It can be 0.5. The preset adjustment factor exists to facilitate subsequent calculations. Therefore, the data value of the preset adjustment factor can be set according to actual needs.

[0069] Indicates The data change similarity between the pressure data and flow data at the pressure data point. The smaller the value, the The stronger the similarity of data changes between the pressure data and the flow data at a pressure data point, the lower the possibility that the pressure data point belongs to a noise data point, and the higher the reliability of the data.

[0070] It represents the absolute difference between the Pearson correlation coefficient and the maximum value of the Pearson correlation coefficient. The smaller the value, the better. The higher the positive correlation between pressure data and flow data in the characteristic data segment of the pressure data point, the smaller the possibility of noise data existing in the characteristic data segment. The smaller the possibility that a pressure data point is noise data, the higher the credibility and reliability.

[0071] Based on the above steps, the stability of each pressure data point can be obtained, and the stability can be further corrected in combination with the correlation between the pressure data and the flow data. After distinguishing the abnormal data and the noise data by the reliability of the corrected pressure data point, the real abnormal situation of each pressure data point can be accurately obtained, and the number of inter-scale expansions can be obtained according to the abnormal situation, that is, the following steps are performed:

[0072] S4: Obtaining the preset number of scales of the pressure data, and determining the number of inter-scale expansions of the characteristic data segment of each pressure data point.

[0073] It should be noted that the reliability of the pressure data point can be used to obtain the number of inter-scale expansions of each pressure data point and expand the characteristic data segment at the initial scale. The lower the reliability of the pressure data point, the more expansion is needed through more inter-scale expansions, thereby introducing more pressure data points to obtain accurate monitoring results for the pressure data point. Therefore, it is necessary to obtain the characteristic data segment of the pressure data point at the initial scale and expand it at different scale numbers.

[0074] For example, the number of preset scales may be 6, which may be set according to actual needs.

[0075] For example, in the embodiment of the present invention, the number of inter-scale expansions is negatively correlated with the reliability of the pressure data point; the number of inter-scale expansions is determined, and the following formula may be specifically referred to:

[0076] ;

[0077] In the formula, Indicates The number of inter-scale expansions of pressure data points, Indicates The reliability of each pressure data point, Indicates the number of expansions between preset scales, Indicates the round-up symbol. Indicates An exponential function with base .

[0078] The preset number of inter-scale expansions may be 30, which may be set according to actual needs. The higher the reliability, the smaller the number of inter-scale expansions; the lower the reliability, the larger the number of inter-scale expansions.

[0079] After obtaining the number of inter-scale expansions of each pressure data point based on the above formula, the characteristic data segment at each scale can be expanded in turn based on the number of inter-scale expansions to obtain the characteristic data segment lengths of the pressure data points at different scales, that is, perform the following steps:

[0080] S5: Expand the characteristic data segment outward on both sides by the number of expansions between scales in turn, obtain the length of the characteristic data segment of the pressure data point at each scale, determine the significance value of the pressure data point, and determine the monitoring result based on the comparison result between the significance value of the pressure data point and the preset threshold.

[0081] For example, when determining the length of the characteristic data segment of the pressure data point at each scale, the characteristic data segment at the previous scale can be expanded on both sides based on the previous scale of the current scale of the pressure data point. The number of single-sided expansions can be half of the number of expansions between scales to obtain the length of the characteristic data segment at the current scale, wherein the length of the characteristic data segment at the current scale includes the length of the characteristic data segment at the previous scale and the length of the number of expansions between scales.

[0082] An example is given to illustrate the process of expanding to obtain the length of the characteristic data segment at each scale: if the number of preset scales of the a-th pressure data point is 3, the length of the characteristic data segment at the initial scale is 61, and the number of scale expansions obtained based on the above steps is 20, then the length of the characteristic data segment of the a-th pressure data point at the second scale is 81, and the length of the characteristic data segment at the third scale is 101. During the expansion process, based on the characteristic data segment of the previous scale, pressure data points can be obtained in equal quantities on both sides of the characteristic data segment. For example, when the characteristic data segment of the a-th pressure data point at the second scale is determined by expansion, 10 pressure data points can be obtained on both sides of the characteristic data segment at the initial scale; similarly, when the characteristic data segment of the a-th pressure data point at the third scale is determined by expansion, 10 pressure data points can be obtained on both sides of the characteristic data segment at the second scale.

[0083] During the expansion of the characteristic data segment, if the number of pressure data points on one side of the characteristic data segment is insufficient, it is supplemented on the other side.

[0084] Based on the above method, the two sides of the characteristic data segment are expanded outward by the number of scale expansions in turn. After the length of the characteristic data segment of the pressure data point at each scale is obtained, the scale value of the pressure data point at each scale can be further determined, and the scale values ​​at all scales are combined to determine the significance value of the pressure data point, wherein the significance value is positively correlated with the stability mean of the pressure data point in the characteristic data segment at each scale.

[0085] For example, in an embodiment of the present invention, when determining the significance value of a pressure data point, the stability mean of all pressure data points in the characteristic data segment of the pressure data point at each scale can be used as the characteristic value of the pressure data point at the corresponding scale; the mean of the difference between the pressure data point and the characteristic value of each pressure data point in the characteristic data segment is used as the scale value of the pressure data point, and finally the significance value of the pressure data point is calculated.

[0086] For example, the significance value of the pressure data point can be calculated by referring to the following formula:

[0087] ;

[0088] In the formula, Indicates The significance value of each pressure data point, Indicates the number of preset scales, Indicates The pressure data point is The scale value under each scale.

[0089] After obtaining the significance value of the pressure data point based on the above method, the final monitoring result can be obtained based on the comparison result between the significance value and the preset threshold:

[0090] For example, in the embodiment of the present invention, when determining the monitoring result according to the comparison result between the significance value of the pressure data point and the preset threshold value, the following two possible situations are included:

[0091] In one possible case, the significance value of the pressure data point is greater than or equal to a preset threshold value. In this case, the monitoring result of the pressure data point is an abnormal data point.

[0092] In another possible case, the significance value of the pressure data point is less than a preset threshold value. In this case, the monitoring result of the pressure data point is a normal data point.

[0093] The preset threshold may be 0.85, which may be set according to actual needs.

[0094] It can be seen that in the embodiment of the present invention, when obtaining the monitoring results of the pressure data in the production process of luggage accessories, the pressure data of the luggage accessories die-casting machine and the flow data of the metal liquid can be obtained, and the pressure data contains multiple pressure data points; with each pressure data point as the center, a characteristic data segment of the pressure data point under the initial scale is preset, and the stability of the pressure data point in the characteristic data segment is determined, and the stability is negatively correlated with the variance of all the pressure data points in the characteristic data segment; the Pearson correlation coefficient between the pressure data and the flow data in the characteristic data segment is determined, and the maximum value of the Pearson correlation coefficient is obtained, and the Pearson correlation coefficient and the maximum value of the Pearson correlation coefficient are obtained. Absolute difference, and calculate the reliability of the pressure data point. Reliability is positively correlated with stability and negatively correlated with absolute difference. Obtain the preset number of scales of pressure data, determine the number of inter-scale expansions of the characteristic data segment of each pressure data point, and the number of inter-scale expansions is negatively correlated with the reliability of the pressure data point. Expand the two sides of the characteristic data segment outward by the number of inter-scale expansions in turn, obtain the length of the characteristic data segment of the pressure data point at each scale, and determine the significance value of the pressure data point. The significance value is positively correlated with the stability mean of the pressure data point in the characteristic data segment at each scale. And determine the monitoring result based on the comparison result of the significance value of the pressure data point with the preset threshold.

[0095] In this way, the present invention combines the scale values ​​of pressure data points at different scales to obtain the significance values ​​of pressure data points and monitors them, thereby avoiding the contingency of monitoring results obtained at a single scale and effectively improving the accuracy of the obtained monitoring results; on this basis, the present invention further combines the flow data that is correlated with the pressure data in the process of calculating each scale value, reduces the influence of noise data on the scale value, effectively improves the accuracy of the obtained scale value, and thus improves the accuracy of the monitoring results.

[0096] After obtaining the monitoring results of various pressure data points in the production of luggage accessories based on the above embodiment, the monitoring results can also be processed:

[0097] For example, in an embodiment of the present invention, after determining the monitoring result, the proportion of all abnormal data points in the pressure data can also be obtained, and when the proportion exceeds a preset alarm threshold, an alarm is issued.

[0098] The preset alarm threshold may be 5%, which may be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0099] In this way, under abnormal circumstances, by sending out alarms, staff can promptly investigate abnormalities in the production process, thereby reducing the possibility of accidents.

[0100] An embodiment of the present invention also discloses an intelligent monitoring system for the progress of the entire production process of luggage accessories, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for intelligent monitoring the progress of the entire production process of luggage accessories according to the present invention is implemented.

[0101] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0102] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0103] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0104] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent monitoring method for the progress of the entire production process of luggage accessories, characterized in that: include: Obtaining pressure data and flow data of a luggage accessories die-casting machine, wherein the pressure data includes a plurality of pressure data points; taking each of the pressure data points as the center, presetting a characteristic data segment of the pressure data point under an initial scale, and determining the stability of the pressure data point in the characteristic data segment, wherein the stability is negatively correlated with the variance of all the pressure data points in the characteristic data segment; The stability of the pressure data points in the characteristic data segment satisfies the relationship: ; In the formula, Indicates The stability of each pressure data point, Indicates The variance of all pressure data points in the characteristic data segment of pressure data points, Indicates In the characteristic data segment of pressure data points, except The variance of other pressure data points besides the pressure data points, Indicates The number of all pressure data points in the characteristic data segment of pressure data points, It represents the slope of the line connecting the starting pressure data point and the ending pressure data point in the characteristic data segment. Indicates the first The pressure data point is The slope of the line connecting the pressure data points, represents the hyperparameter, represents the normalization function, Indicates the absolute value symbol; Determine the Pearson correlation coefficient between the pressure data and the flow data in the characteristic data segment, obtain the maximum value of the Pearson correlation coefficient, and obtain the absolute difference between the Pearson correlation coefficient and the maximum value of the Pearson correlation coefficient, wherein the maximum value of the Pearson correlation coefficient is 1; and calculate the reliability of the pressure data point, wherein the reliability is positively correlated with the stability and negatively correlated with the absolute difference; obtain the preset number of scales of the pressure data, determine the number of inter-scale expansions of the characteristic data segment of each pressure data point, wherein the number of inter-scale expansions is negatively correlated with the reliability of the pressure data point; The calculating the reliability of the pressure data point comprises: In the flow data, a flow data point at the same sampling time as a pressure data point is obtained; ; In the formula, Indicates The reliability of each pressure data point, Indicates The stability of each pressure data point, Indicates The pressure value of each pressure data point, Indicates The flow value corresponding to the pressure data point is Indicates The mean pressure of the characteristic data segment of the pressure data points, Indicates The characteristic data segment of each pressure data point corresponds to the mean flow rate of the sampling time period in the flow data. Represents the Pearson correlation coefficient of pressure data and flow data, represents the hyperparameter, and Both represent preset adjustment factors. represents the normalization function, represents the exponential function with base e, Indicates the absolute value symbol; Sequentially expand the two sides of the characteristic data segment outward by the number of expansions between scales, respectively obtain the length of the characteristic data segment of the pressure data point at each scale, determine the significance value of the pressure data point, and the significance value is positively correlated with the stability mean of the pressure data point in the characteristic data segment at each scale; and determine the monitoring result according to the comparison result of the significance value of the pressure data point with the preset threshold value; Determining the significance value of the pressure data point includes: Taking the stability mean of all pressure data points in the characteristic data segment of the pressure data point at each scale as the characteristic value of the pressure data point at the corresponding scale; The mean of the difference between the pressure data point and the characteristic values ​​of each pressure data point in the characteristic data segment is used as the scale value of the pressure data point; and the significance value of the pressure data point is calculated: ; In the formula, Indicates The significance value of each pressure data point, Indicates the number of preset scales, Indicates The pressure data point is The scale value under each scale.

2. The method for intelligently monitoring the progress of the entire production process of luggage accessories according to claim 1 is characterized in that: The method of obtaining the pressure data and the flow data of the metal liquid of the luggage accessories die-casting machine also includes: The initial pressure data of the die-casting machine and the initial flow data of the metal liquid are obtained by collecting equipment, and the initial pressure data and the initial flow data are preprocessed to obtain the pressure data of the die-casting machine and the flow data of the metal liquid.

3. The method for intelligently monitoring the progress of the entire production process of luggage accessories according to claim 1 is characterized in that: The number of expansions between the scales satisfies the relationship: ; In the formula, Indicates The number of inter-scale expansions of pressure data points, Indicates The reliability of each pressure data point, Indicates the number of expansions between preset scales, Indicates the round-up symbol. Represents an exponential function with base e.

4. The method for intelligently monitoring the progress of the entire production process of luggage accessories according to claim 1 is characterized in that: Determining the monitoring result according to the comparison result between the significance value of the pressure data point and the preset threshold value includes: When the significance value of the pressure data point is greater than or equal to a preset threshold, the monitoring result of the pressure data point is an abnormal data point; When the significance value of the pressure data point is less than a preset threshold, the monitoring result of the pressure data point is a normal data point.

5. The method for intelligently monitoring the progress of the entire production process of luggage accessories according to claim 1 or 4, characterized in that: After determining the monitoring result, the following steps are further included: The proportion of all abnormal data points in the pressure data is obtained, and when the proportion exceeds a preset alarm threshold, an alarm is issued.

6. The intelligent monitoring system for the whole process of luggage accessories production is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method for intelligently monitoring the progress of the entire production process of luggage accessories according to any one of claims 1 to 5 is implemented.